Computer Rating System Prediction Results for College Football (NCAA IA)

20 Season Totals

System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
Massey *0.776880.5110511.80201.2431223.55037228983185177
Pigskin Index0.756300.4947511.54050.6110216.060714540174330337
System Average0.752100.5014411.57230.4370217.049714537177349347
Atomic Football0.752100.4971311.51200.8409216.111714537177346350
Dokter Entropy0.750700.5165511.44440.7752212.719714536178359336
Hank Trexler0.750350.4923811.8850-0.0084231.237713535178323333
Moore Power Ratings0.749300.5172911.71120.5256225.807714535179359335
Billingsley+0.749300.5093511.75860.4208228.385714535179354341
Laz Index0.749300.5014411.66670.1511221.865714535179348346
NationalSportsRankings0.748480.4846011.75920.3506225.182656491165299318
System Median0.747900.4919711.54950.4387216.008714534180337348
Edward Kambour0.746500.5245011.64920.7182219.689714533181364330
ARGH Power Ratings0.742300.5104512.20170.6674239.155714530184342328
Stat Fox0.739500.5038211.66251.6683221.267714528186330325
Dunkel Index0.739130.4971211.84541.1091227.489713527186345349
Computer Adjusted Line0.738100.5166111.26121.0917206.163714527187140131
Sagarin Predictive0.738100.5043111.75290.6497224.315714527187351345
Marsee0.737730.4762612.68581.9677262.714713526187321353
Nutshell Girl0.736690.5258612.2668-0.1733244.838714526188366330
Born Power Index0.736690.4899112.08340.4529240.313714526188340354
Keeper0.736690.4964012.07171.5916234.506714526188345350
NutShell Combo0.736690.5245011.70030.1868221.595714526188364330
Ashby AccuRatings0.736690.4916311.75630.1601224.631714526188323334
Line (updated)0.7338911.26541.1814206.152714524190
Linear Regression0.733870.5276211.89220.9067228.93037227399191171
Howell0.733520.5174012.00220.0065232.849713523190342319
Line (opening)0.732490.4974211.41740.8249212.248714523191289292
Lee Burdorf0.732490.5036312.05810.4940238.303714523191347342
Billingsley0.732490.5287412.5430-0.0059253.321714523191368328
Covers.com0.732490.5348812.09120.0708236.518714523191368320
CPA Rankings0.732040.5053912.26320.1163244.168668489179328321
Anderson/Hester *0.731180.4930712.51990.7481249.200372272100178183
Schmidt Comp. Ratings0.731090.4971312.05360.1328238.557714522192346350
Bassett Model0.729960.4891812.46071.8703248.630711519192339354
Payne Power Ratings0.729170.4928612.4982-0.1746255.153576420156276284
NutShell Sports0.728290.5143712.21800.5398241.651714520194358338
Bihl System0.727060.4878611.84860.8618227.504425309116201211
Beck Elo0.726890.5079412.08900.2810239.203714519195352341
Sagarin0.726890.5000011.95330.4593234.340714519195348348
Dave Congrove0.726890.5100612.0814-0.1209235.237714519195355341
Least Squares w/ HFA0.725810.5221013.78620.7620311.808372270102189173
Stephen Kerns0.725490.5258612.52910.7475256.894714518196366330
Frank Alder0.725490.4985612.6280-0.4457260.100714518196347349
Super List0.725490.5050413.58150.9087292.143714518196351344
Massey Consensus0.725490.5057512.05170.6875237.293714518196352344
CPA Retro0.724550.5046213.3387-0.0054286.861668484184328322
PerformanZ Ratings0.724090.4827612.6587-0.0329264.096714517197336360
Imes Comprank0.723450.4847312.4674-0.0253250.253499361138238253
Harmon Forcast0.723210.4896712.2321-1.4048247.691672486186308321
Catherwood Ratings0.722690.5000011.92721.2661236.606714516198326326
Logistic Regression0.717740.5359115.0370-2.4933369.468372267105194168
DP Dwiggins0.711960.5159312.4536-3.3892250.857677482195340319
Warren Claassen0.708680.5043112.9084-0.4963270.781714506208351345
Sagarin Elo0.707280.5071812.74870.2918263.889714505209353343
Wolfe *0.706990.4944813.46981.5001288.803372263109179183
Sportrends0.705550.4931912.7319-0.1486259.673703496207326335
TW Rankings0.701520.5023613.0547-0.1404283.666660463197319316
CF By the Numbers0.699680.4390211.9457-0.5272228.92931321994126161
Colley Rankings *0.698920.5027612.92310.8179270.791372260112182180
Martien Maas0.688210.4921613.07660.4696276.537526362164251259
Tom Benson0.675560.4870314.95173.2272341.119712481231338356

* This system does not make predictions.  I make predictions for this
  system by translating it to a new scale that allows for making predictions.



Retrodictive records are found by taking the ratings from the current week
and applying them to the entire season to date.

The ideal system would be one that has the highest correct game decisions,
has the smallest mean error(deviation from the actual game result), and has
a bias of zero.

Mean Error = average[abs(prediction-actual)]

      Bias = agerage(prediction - actual)

      Std. = Standard Deviation of individual game biases